Suppression of sampling moire in color printing by spline-based least-squares prefiltering

Many image processing systems, including those for printing applications, need sampling conversions for the representation of an image from one lattice to another. For example in the case of printing, classical halftoning requires new sample values on the halftone lattice. Although often considered as a straightforward procedure, resampling can cause so-called sampling moire due to aliasing. These artifacts are often very noticeable and as such undesirable, in particular for high-quality printing. In color printing, each color separation uses its own halftone lattice. Therefore, moire patterns will not only display an unexpected new frequency and orientation, but also influence the color appearance itself. These artifacts are frequently encountered in commercial (even high-quality) printing since the interpolation algorithms used in RIPs are simple (e.g., bilinear interpolation) and do not take into account the nature of the target lattice. Approaches such as simple low-pass filtering unacceptably blur the edges, while manual selective smoothing by an operator is very time-consuming. This paper proposes an optimal prefilter which is based on the least-squares linear resampling paradigm. Our approach requires proper discrete/continuous models, i.e., for both the source and the target lattices, and computes the associated reconstruction function which minimizes the error between the representations in the continuous domain. The reconstruction function jointly takes into account the Nyquist areas of every color separation using a novel hexagonal spline model resulting into an optimal prefilter before halftoning. Experimental results show that after prefiltering, the images are much less prone to moire while not suffering from noticeable edge blurring. 2002 Elsevier Science B.V. All rights reserved.